A Multi-Armed Bandit Model Selection for Cold-Start User Recommendation

  title={A Multi-Armed Bandit Model Selection for Cold-Start User Recommendation},
  author={Cr{\'i}cia Z. Fel{\'i}cio and Kl{\'e}risson Vin{\'i}cius Ribeiro Paix{\~a}o and C{\'e}lia A. Zorzo Barcelos and Philippe Preux},
  journal={Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization},
How can we effectively recommend items to a user about whom we have no information? This is the problem we focus on in this paper, known as the cold-start problem. In most existing works, the cold-start problem is handled through the use of many kinds of information available about the user. However, what happens if we do not have any information? Recommender systems usually keep a substantial amount of prediction models that are available for analysis. Moreover, recommendations to new users… 

Figures and Tables from this paper

A contextual approach to improve the user's experience in interactive recommendation systems

A new contextual approach to initialize the bandit models is proposed to address both exploration and exploitation goals since the first recommendations by mixing entropic and popular items, which maximizes the user's satisfaction in the long-term run.

User cold-start problem in Multi-Armed Bandits: when the first recommendations guide the user’s experience

This paper proposes a new approach to balance exploration and exploitation in the first interactions of a new user and statistically outperforms ten benchmarks in the literature in the long run, based on the Active Learning theory.

Assessing and improving recommender systems to deal with user cold-start problem

This thesis proposes 4 approaches to deal with user cold-start problem using existing models available for analysis in the recommender systems and evaluated the proposed approaches in terms of prediction quality and ranking quality in real-world datasets under different recommendation domains.

Fast and Accurate User Cold-Start Learning Using Monte Carlo Tree Search

It is found that this new MCTS-based cold-start approach is able to consistently quickly identify the preferences of a user with significantly higher accuracy than with either a decision-tree or a state of the art bandit-based approach without incurring higher regret.

A Bandit-Based Ensemble Framework for Exploration/Exploitation of Diverse Recommendation Components

This work presents an extension of Thompson Sampling bandit policy for orchestrating the collection of base recommendation algorithms for e-commerce. We focus on the problem of item-to-item

Cluster-Based Bandits: Fast Cold-Start for Recommender System New Users

This paper introduces a new type of online learning algorithm, cluster-based bandits, that exploits the fact that users can often be grouped into clusters based on the similarity of their preferences, and this allows accelerated learning of new user preferences.

Efficient Context-Aware Sequential Recommender System

This work proposes to store the covariance matrix of the previously seen contexts in a compressed space, without losing too much in terms of recommendation quality in the era of big-data content features.

The impact of first recommendations based on exploration or exploitation approaches in recommender systems' learning

Experimental results show that the combination of exp-exp at first user's interactions improves the system's effectiveness without adding more effort to users.

Survey of multi­armed bandit algorithms applied to recommendation systems

—The main goal of this paper is to introduce the reader to the multi­armed bandit algorithms of different types and to observe how the industry leveraged them in advancing recommendation systems. We

Proposed Recommender System For Solving Cold Start Issue Using k-means Clustering and Reinforcement Learning Agent

  • A. B. A. Alwahhab
  • Computer Science
    2020 2nd Annual International Conference on Information and Sciences (AiCIS)
  • 2020
A reinforcement learning recommender system that provides the automatic systems of multi-armed bandits which are learning and improving its efficiency from experience without being explicitly programmed is suggested.



Mixing bandits: a recipe for improved cold-start recommendations in a social network

This work proposes two novel strategies leveraging neighborhood estimates to improve the learning rate of bandits for cold-start users, extending the well-known UCB1 algorithm and inheriting its asymptotically optimal guarantees.

Preference-Like Score to Cope with Cold-Start User in Recommender Systems

This work contributes to this line of work comparing several matrix factorization based SRS under full cold-start user scenario, and proposing a general model selection approach, called ToSocialRec, that leverages existing recommendation models to offer items for new users.

Bandits and Recommender Systems

The combination of matrix factorization and bandit algorithms to solve the on-line recommendation problem is driven by considering the recommendation problem as a feedback controlled loop and leads to interactions between the representation learning, and the recommendation policy.

Pairwise preference regression for cold-start recommendation

P predictive feature-based regression models are proposed that leverage all available information of users and items, such as user demographic information and item content features, to tackle cold-start problems and scale efficiently as a linear function of the number of observations.

Cold-Start Item and User Recommendation with Decoupled Completion and Transduction

This paper proposes a novel algorithmic framework based on matrix factorization that simultaneously exploits the similarity information among users and items to alleviate the cold-start problem and is believed to be the first algorithm that addresses theColdstart problem with provable guarantees.

Multi-level preference regression for cold-start recommendations

This work designs a new convex framework for cold-start recommendations, multi-level preference regression (MPR), directly to predict the ratings rather than latent profiles, and demonstrates that the proposed model can achieve the state of the art in the usercold-start scenario and the best performance in other scenarios.

Ensemble contextual bandits for personalized recommendation

A meta-bandit paradigm is employed that places a hyper bandit over the base bandits, to explicitly explore/exploit the relative importance of base bandits based on user feedbacks to obtain robust predicted click-through rate (CTR) of web objects.

Cold-Start Recommendation with Provable Guarantees: A Decoupled Approach

This paper proposes a novel and general algorithmic framework based on matrix completion that simultaneously exploits the similarity information among users and items to alleviate the cold-start problem and is believed to be the first algorithm that addresses theColdstart problem with provable guarantees on performance.

Switching hybrid for cold-starting context-aware recommender systems

A switching hybrid solution that exploits a custom selection of two CARS algorithms, each suited for a particular cold-start situation, and switches between these algorithms depending on the detected recommendation situation (new user, new item or new context).